相关论文: PEPA: a Persistently Autonomous Embodied Agent wit…

Reinforcement Learning is a machine learning methodology that has demonstrated strong performance across a variety of tasks. In particular, it plays a central role in the development of artificial autonomous agents. As these agents become…

Large language models (LLMs) increasingly serve as the central control unit of AI agents, yet current approaches remain limited in their ability to deliver personalized interactions. While Retrieval Augmented Generation enhances LLM…

Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to hundreds of thousands of examples), yet remain vulnerable to novel attack vectors and distributional shifts. We…

In this exploratory paper we introduce the problem of cognitive agents that learn how to modify their environment according to local sensing to reach a global goal. We concentrate on discrete dynamics (cellular automata) on a…

Autonomous agents play a crucial role in advancing Artificial General Intelligence, enabling problem decomposition and tool orchestration through Large Language Models (LLMs). However, existing paradigms face a critical trade-off. On one…

The embedding of Large Language Models (LLMs) into autonomous agents is a rapidly developing field which enables dynamic, configurable behaviours without the need for extensive domain-specific training. In our previous work, we introduced…

The standard theory of model-free reinforcement learning assumes that the environment dynamics are stationary and that agents are decoupled from their environment, such that policies are treated as being separate from the world they…

Embodied agents have shown promising generalization capabilities across diverse physical environments, making them essential for a wide range of real-world applications. However, building versatile embodied agents poses critical challenges…

Robots operating in human spaces must be able to engage in natural language interaction with people, both understanding and executing instructions, and using conversation to resolve ambiguity and recover from mistakes. To study this, we…

This letter introduces ERRA, an embodied learning architecture that enables robots to jointly obtain three fundamental capabilities (reasoning, planning, and interaction) for solving long-horizon language-conditioned manipulation tasks.…

Modern AI agents suffer from a fundamental identity problem: when context windows overflow and conversation histories are summarized, agents experience catastrophic forgetting -- losing not just information, but continuity of self. This…

Collaborative reasoning with multiple agents offers the potential for more robust and diverse problem-solving. However, existing approaches often suffer from homogeneous agent behaviors and lack of reflective and rethinking capabilities. We…

Self-anthropomorphism in robots manifests itself through their display of human-like characteristics in dialogue, such as expressing preferences and emotions. Our study systematically analyzes self-anthropomorphic expression within various…

The development of artificial agents for social interaction pushes to enrich robots with social skills and knowledge about (local) social norms. One possibility is to distinguish the expressive and the functional orders during a human-robot…

We present Confidence-Based Autonomy (CBA), an interactive algorithm for policy learning from demonstration. The CBA algorithm consists of two components which take advantage of the complimentary abilities of humans and computer agents. The…

Many tasks in control, robotics, and planning can be specified using desired goal configurations for various entities in the environment. Learning goal-conditioned policies is a natural paradigm to solve such tasks. However, current…

Autonomous agents powered by large language models (LLMs) have shown impressive capabilities in tool manipulation for complex task-solving. However, existing paradigms such as ReAct rely on sequential reasoning and execution, failing to…

The rapid development and adoption of Generative AI (GAI) technology in the form of chatbots such as ChatGPT and Claude has greatly increased interest in agentic machines. This paper introduces the Autonomous Cognitive Entity (ACE) model, a…

Learning manipulable representations of the world and its dynamics is central to AI. Joint-Embedding Predictive Architectures (JEPAs) offer a promising blueprint, but lack of practical guidance and theory has led to ad-hoc R&D. We present a…

Recent research on proactive conversational agents (PCAs) mainly focuses on improving the system's capabilities in anticipating and planning action sequences to accomplish tasks and achieve goals before users articulate their requests. This…